snipara-companion 1.1.49 → 1.2.0

package/README.md

@@ -34,10 +34,14 @@ For Codex, the primary integration remains Hosted MCP plus `AGENTS.md`.
 
 - `create-snipara` installs `snipara-companion` by default for managed workflow commands.
 - `snipara-companion` is still skippable with `--profile hosted-only` or `--skip-companion`.
-- This package does not currently scaffold a Codex-specific preset.
-- Use it when compaction-safe phase commits, local doctor checks, or shared helper workflows are useful.
+- Use it when compaction-safe phase commits, Project Intelligence briefs, local doctor checks, or shared helper workflows are useful.
+- Use `workflow scaffold --preset project-intelligence-continuity-layer` for roadmap-sized Project Intelligence work that needs phase commits.
 - If an agent session exposes only a subset of Snipara tools, use `snipara_help(list_all=true)` in that session before concluding a tool is unavailable.
 
+## Configuring MCP Tool Surfaces
+
+The MCP server advertises different tool surfaces depending on the `SNIPARA_EXPOSED_SURFACES` environment variable. To expose companion tools directly in the advertised manifest, set `SNIPARA_EXPOSED_SURFACES=inline,companion` on the MCP server. This is optional: companion tools are still callable by name on demand via `snipara_help`, even if not advertised.
+
 ## Installation
 
 ```bash
@@ -54,6 +58,12 @@ yarn global add snipara-companion
 snipara-companion
 ```
 
+## New In 1.2.0
+
+- Adds `snipara-companion intelligence brief` for a local Project Intelligence brief that composes hosted resume context, memory health, and code impact into one agent-ready output.
+- Adds `workflow scaffold --preset project-intelligence-continuity-layer` for the full memory + code graph + workflow continuity roadmap.
+- Updates generated agent workflow instructions so new work can call the Project Intelligence brief before risky changes and scaffold the roadmap preset for multi-phase delivery.
+
 ## New In 1.1.15
 
 - Expands `init --client` to Claude Code, Cursor, Windsurf, Codex, Gemini, Mistral, ChatGPT, VS Code, Continue, and custom MCP clients.
@@ -332,6 +342,8 @@ npx -y snipara-companion@latest task-commit --summary "Shipped auth refactor" --
 
 snipara-companion query --query "auth middleware"
 snipara-companion query --query "who calls src.mcp_transport.handle_call_tool" --follow-recommendation
+snipara-companion intelligence brief --task "ship auth hardening" --changed-files apps/web/src/lib/auth.ts tests/auth.test.ts --diff-summary "auth hardening"
+snipara-companion workflow scaffold --preset project-intelligence-continuity-layer --output .snipara/workflow/plans/project-intelligence-plan.json
 snipara-companion workflow start --goal "ship auth hardening" --plan-file ./plan.json
 snipara-companion workflow status
 snipara-companion workflow phase-start context
@@ -445,6 +457,32 @@ snipara-companion task-commit --summary "Validated PR Answer Pack release docs"
 Only add a dedicated `snipara-companion github answer-packs` command if Snipara
 ships a public API for manual regeneration or inspection outside the dashboard.
 
+### Project Intelligence Briefs
+
+Use `intelligence brief` when a task needs one local entrypoint for continuity,
+memory authority, and code impact:
+
+```bash
+snipara-companion intelligence brief \
+  --task "add workspace invite policy" \
+  --changed-files apps/web/src/lib/workspace-invites.ts apps/web/src/lib/workspace-invites.test.ts \
+  --diff-summary "workspace invite policy change"
+```
+
+The command calls hosted `snipara_resume_context`, `snipara_memory_health`, and,
+when changed files are provided, `snipara_code_impact`. It prints continuity
+signals, memory health, risk and verification hints, degraded surfaces, and the
+next companion commands to keep the workflow resumable.
+
+For the full Project Intelligence and Continuity Layer roadmap, scaffold the
+built-in managed workflow plan:
+
+```bash
+snipara-companion workflow scaffold \
+  --preset project-intelligence-continuity-layer \
+  --output .snipara/workflow/plans/project-intelligence-plan.json
+```
+
 ### Context vs Memory
 
 - Use `snipara-companion query`, `shared-context`, and `load-document` for source truth.
@@ -461,7 +499,9 @@ Semantics:
 - `snipara-companion workflow run --mode full` = session bootstrap + context query + automatic structural follow-up + hosted plan
 - `snipara-companion workflow run --mode orchestrate` = explicit hosted orchestrator flow for deeper multi-step exploration; use the Python `snipara-orchestrator` package for production gates and htasks
 - `snipara-companion workflow run` = suggests Snipara Sandbox when the query calls for validation, execution, data transforms, or heavier FULL/orchestrated work
+- `snipara-companion intelligence brief` = one local Project Intelligence brief that combines resume context, memory health, and code impact for a task
 - `snipara-companion workflow start --plan-file` = records the visible LLM plan locally so phase state survives agent compaction; prefer JSON plans with explicit ids for stable machine phase state
+- `snipara-companion workflow scaffold --preset project-intelligence-continuity-layer` = creates a four-phase managed plan for memory authority, code impact, continuity summaries, and release/docs surfaces
 - `snipara-companion workflow phase-start` = marks the current phase and prints the required Snipara context gate plus code-impact / symbol-card gates; runtime-marked phases also get a stable Snipara Sandbox session binding
 - `snipara-companion workflow runtime-checkpoint` = captures a resume-ready Snipara Sandbox checkpoint for one phase using local workflow state plus a hosted automation event when configured
 - `snipara-companion workflow phase-commit` = calls hosted `snipara_end_of_task_commit` for that phase, updates local state, and advances the next phase

package/dist/index.d.ts

@@ -1046,6 +1046,36 @@ declare function detectReleaseSurfacesFromFiles(root: string, files: string[]):
 declare function getStagedFiles(root: string): string[];
 declare function runMemoryGuardCheck(options?: MemoryGuardCheckOptions): Promise<MemoryGuardCheckResult>;
 
+interface ProjectIntelligenceBriefOptions {
+    task?: string;
+    branch?: string;
+    changedFiles?: string[];
+    recentFiles?: string[];
+    diffSummary?: string;
+    maxTokens?: number;
+    skipImpact?: boolean;
+    skipMemoryHealth?: boolean;
+    json?: boolean;
+}
+interface ProjectIntelligenceBrief {
+    version: "project-intelligence-brief-v1";
+    generatedAt: string;
+    branch?: string;
+    task?: string;
+    changedFiles: string[];
+    recentFiles: string[];
+    resumeContext?: Record<string, unknown>;
+    memoryHealth?: Record<string, unknown>;
+    codeImpact?: Record<string, unknown>;
+    errors: Array<{
+        surface: string;
+        message: string;
+    }>;
+    suggestedCommands: string[];
+}
+declare function buildProjectIntelligenceBrief(options: ProjectIntelligenceBriefOptions): Promise<ProjectIntelligenceBrief>;
+declare function projectIntelligenceBriefCommand(options: ProjectIntelligenceBriefOptions): Promise<void>;
+
 type SyncDocumentKind = "DOC" | "BINARY";
 type WorkflowMode = "lite" | "standard" | "auto" | "full" | "orchestrate";
 type OnboardFolderMode = "auto" | "business_context" | "code_project" | "mixed";
@@ -1056,7 +1086,7 @@ type ReindexMode = "incremental" | "full";
 type TaskCommitOutcome = "completed" | "partial" | "blocked" | "abandoned";
 declare const WORKFLOW_STATE_RELATIVE_PATH: string;
 declare const WORKFLOW_PLANS_RELATIVE_DIR: string;
-type WorkflowPlanPreset = "memory-backend-unification";
+type WorkflowPlanPreset = "memory-backend-unification" | "project-intelligence-continuity-layer";
 interface WorkflowPlanScaffoldDocument {
     preset: WorkflowPlanPreset;
     mode: "full";
@@ -1589,4 +1619,4 @@ interface WrittenOrchestratorHandoff {
 declare function buildOrchestratorHandoff(options: OrchestratorHandoffOptions): OrchestratorHandoffArtifact;
 declare function writeOrchestratorHandoff(options: OrchestratorHandoffOptions): WrittenOrchestratorHandoff;
 
-export { AUTOMATION_MANIFEST_RELATIVE_PATH, AutomationInstallConflictError, AutomationUnsupportedHookBundleError, ORCHESTRATOR_HANDOFF_RELATIVE_PATH, TEAM_SYNC_STATE_RELATIVE_PATH, WORKFLOW_PLANS_RELATIVE_DIR, WORKFLOW_STATE_RELATIVE_PATH, buildAutomationInstallPlan, buildCanonicalEvent, buildJournalCheckpointEntry, buildOnboardFolderManifest, buildOrchestratorHandoff, buildSyncDocumentsDryRun, buildTeamSyncHandoffRecord, buildTeamSyncStartWorkRecord, buildTeamSyncSummary, buildToolCallPayload, buildToolResultPayload, buildWorkflowPhaseCommitSummary, buildWorkflowPlanScaffold, categoryFromGuardTag, classifyToolResult, collectSyncDocuments, collectSyncDocumentsInput, createClient, createEmptyTeamSyncState, createLocalQueryCache, detectReleaseSurfacesFromFiles, detectRuntimeEnvironment, extractCommandFromToolInput, extractFilesFromToolInput, formatOrchestratorRecommendationReason, formatStuckGuardDecision, getAutomationManifestPath, getAutomationStatus, getConfigPath, getOrchestratorRecommendation, getPlanStepDisplayTitle, getStagedFiles, getStuckGuardInjection, getTeamSyncStatePath, installAutomationBundle, listProjectsForApiKey, loadAutomationManifest, loadConfig, loadTeamSyncState, normalizeGuardTag, normalizeWorkflowPlanInput, resolveQueryFromToolInput, runMemoryGuardCheck, saveConfig, saveTeamSyncState, shouldSuggestOrchestratorForWorkflow, shouldSuggestRuntimeForWorkflow, writeOrchestratorHandoff };
+export { AUTOMATION_MANIFEST_RELATIVE_PATH, AutomationInstallConflictError, AutomationUnsupportedHookBundleError, ORCHESTRATOR_HANDOFF_RELATIVE_PATH, TEAM_SYNC_STATE_RELATIVE_PATH, WORKFLOW_PLANS_RELATIVE_DIR, WORKFLOW_STATE_RELATIVE_PATH, buildAutomationInstallPlan, buildCanonicalEvent, buildJournalCheckpointEntry, buildOnboardFolderManifest, buildOrchestratorHandoff, buildProjectIntelligenceBrief, buildSyncDocumentsDryRun, buildTeamSyncHandoffRecord, buildTeamSyncStartWorkRecord, buildTeamSyncSummary, buildToolCallPayload, buildToolResultPayload, buildWorkflowPhaseCommitSummary, buildWorkflowPlanScaffold, categoryFromGuardTag, classifyToolResult, collectSyncDocuments, collectSyncDocumentsInput, createClient, createEmptyTeamSyncState, createLocalQueryCache, detectReleaseSurfacesFromFiles, detectRuntimeEnvironment, extractCommandFromToolInput, extractFilesFromToolInput, formatOrchestratorRecommendationReason, formatStuckGuardDecision, getAutomationManifestPath, getAutomationStatus, getConfigPath, getOrchestratorRecommendation, getPlanStepDisplayTitle, getStagedFiles, getStuckGuardInjection, getTeamSyncStatePath, installAutomationBundle, listProjectsForApiKey, loadAutomationManifest, loadConfig, loadTeamSyncState, normalizeGuardTag, normalizeWorkflowPlanInput, projectIntelligenceBriefCommand, resolveQueryFromToolInput, runMemoryGuardCheck, saveConfig, saveTeamSyncState, shouldSuggestOrchestratorForWorkflow, shouldSuggestRuntimeForWorkflow, writeOrchestratorHandoff };