feat(context): add Recent-Only and RAG modes

.env.example

@@ -46,6 +46,12 @@ BCG_GRAPH_START_TIMEOUT="120"
 BCG_GRAPH_TIMEOUT_MS="300000"
 BCG_RECENT_TURNS="2"
 
+# Optional local RAG context tuning. The default database path is session-local
+# under ~/.bcg/agent/rag; set BCG_RAG_DB_PATH only to override it.
+BCG_RAG_DB_PATH=""
+BCG_RAG_TOP_K="6"
+BCG_RAG_MAX_CHARS="12000"
+
 # Optional local GPU service profiles. These names are deliberately separate
 # from MODEL, which is the remote/API model used by Agent rollouts.
 VLLM_MODEL=""

agent-cli/README.md

@@ -6,12 +6,17 @@ Interactive terminal Agent for
 The public command is `bcg`, provided by the Python package. This Node package
 installs the internal `bcg-agent` runtime used by that launcher.
 
-The runtime supports three session-level context modes. Default retains normal
-full context with compaction. BCG and Summary both pin the initial user input,
-retain a configurable number of recent completed turns, and evict older turns
-in the same batches. BCG converts those batches into a belief graph; Summary
-updates one rolling LLM summary. Either memory block is injected into the
-system prompt.
+The runtime supports five session-level context modes. Every bounded mode
+permanently pins the initial user input and retains a configurable number of
+recent completed turns:
+
+- **Default** keeps the full conversation with automatic compaction.
+- **Recent-Only** drops older turns and leaves the system prompt unchanged.
+- **RAG** stores dropped turns in a session-local SQLite FTS5 database, queries
+  it with the recent raw turns, and injects retrieved history into the system
+  prompt.
+- **Summary** compresses dropped turns into one rolling LLM summary.
+- **BCG** converts dropped turns into a confidence-aware belief graph.
 
 Configuration and sessions live under `~/.bcg/agent/`. API credentials can be
 entered with `/login`; custom OpenAI-compatible endpoints use

agent-cli/src/core/agent-session.ts

@@ -62,7 +62,7 @@ import {
 	prepareCompaction,
 	shouldCompact,
 } from "./compaction/index.ts";
-import { getSessionContextMode } from "./context/context-mode.ts";
+import { getSessionContextMode, usesBoundedContext } from "./context/context-mode.ts";
 import { DEFAULT_THINKING_LEVEL } from "./defaults.ts";
 import { exportSessionToHtml, type ToolHtmlRenderer } from "./export-html/index.ts";
 import { createToolHtmlRenderer } from "./export-html/tool-renderer.ts";
@@ -1776,8 +1776,8 @@ export class AgentSession {
 	 */
 	async compact(customInstructions?: string): Promise<CompactionResult> {
 		const contextMode = getSessionContextMode(this.sessionManager);
-		if (contextMode === "bcg" || contextMode === "summary") {
-			throw new Error("Traditional compaction is disabled in BCG and Summary modes.");
+		if (usesBoundedContext(contextMode)) {
+			throw new Error("Traditional compaction is disabled in bounded-context modes.");
 		}
 		this._disconnectFromAgent();
 		await this.abort();
@@ -1950,7 +1950,7 @@ export class AgentSession {
 	 */
 	private async _checkCompaction(assistantMessage: AssistantMessage, skipAbortedCheck = true): Promise<boolean> {
 		const contextMode = getSessionContextMode(this.sessionManager);
-		if (contextMode === "bcg" || contextMode === "summary") {
+		if (usesBoundedContext(contextMode)) {
 			return false;
 		}
 		const settings = this.settingsManager.getCompactionSettings();
@@ -2226,7 +2226,7 @@ export class AgentSession {
 	/** Whether auto-compaction is enabled */
 	get autoCompactionEnabled(): boolean {
 		const contextMode = getSessionContextMode(this.sessionManager);
-		return contextMode !== "bcg" && contextMode !== "summary" && this.settingsManager.getCompactionEnabled();
+		return !usesBoundedContext(contextMode) && this.settingsManager.getCompactionEnabled();
 	}
 
 	async bindExtensions(bindings: ExtensionBindings): Promise<void> {

agent-cli/src/core/context/context-mode.ts

@@ -3,8 +3,18 @@ import type { ContextManagementProvider } from "../settings-manager.ts";
 
 export const CONTEXT_MODE_ENTRY_TYPE = "bcg.context_mode";
 
+export function usesBoundedContext(provider: ContextManagementProvider | undefined): boolean {
+	return provider === "bcg" || provider === "summary" || provider === "recent-only" || provider === "rag";
+}
+
 function isContextManagementProvider(value: unknown): value is ContextManagementProvider {
-	return value === "default" || value === "bcg" || value === "summary";
+	return (
+		value === "default" ||
+		value === "bcg" ||
+		value === "summary" ||
+		value === "recent-only" ||
+		value === "rag"
+	);
 }
 
 export function getSessionContextMode(sessionManager: SessionManager): ContextManagementProvider | undefined {